Open-source multAIplayer Alpha makes Codex a shared team coding workspace
jxnlco · x · 2026-07-22
Open-source multAIplayer Alpha turns Codex into a shared team workspace
The post reintroduces multAIplayer Alpha, a free open-source macOS app and CLI for trusted teams to build together with Codex.
What it does
- lets teammates discuss work in a shared room
- steers one shared local Codex session
- lets people review changes, hand off hosting, and continue from another machine
- includes Monaco editing, diffs, terminals, web previews, Git, PRs, and CI
- supports local development previews through Cloudflare Quick Tunnels
Security and collaboration model
- teamwork is shared through a free hosted relay, with self-hosting available
- encrypted with an unaudited MLS implementation
- uses host-approved room context rather than a custom system prompt
- the active host controls the project, sandbox, tools, and approvals
The main idea is a collaborative coding-agent environment where multiple teammates can coordinate around one AI session instead of each working in isolation.
More from coding & agent
- Agent harness providers are asked to support in-place tool updates without restarts — GabGarrett · 2026-07-22
- Bolt adds stacked team skills that can all trigger from one prompt — damianplayer · 2026-07-22
- A new RL finding says the training harness may induce generalization — inductionheads · 2026-07-22
- Coding agents are making stagnant enterprise software feel alive again — yunta_tsai · 2026-07-22
- Lakuna Router: Making AI Models 'Audition' for Real-World Workflows — Due_Hovercraft6497 · 2026-07-22
- LangChain says dcode added native browser control with one /goal command — LangChain · 2026-07-22